报告题目：   A novel control method for solving high-dimensional Hamiltonian systems through deep neural networks

报告摘要：  A novel control method is proposed to solve a high-dimensional stochastic Hamiltonian system with boundary conditions, which is essentially a Forward Backward Stochastic Differential Equation (FBSDE in short). Different from existing methods, we first formulate a stochastic optimal control problem whose extended Hamiltonian system is exactly the system to be solved. Then two different algorithms to calculate the stochastic optimal control via deep neural networks are designed respectively. Comparing with the Deep FBSDE method developed by E et al.（2017）, our proposed algorithms demonstrate more stable performance. （With Shige Peng, Ying Peng and Xichuan Zhang）.

报告时间：2024年11月21日 11：00：00-12：00

报告地点： 统计与数据科学学院 106

报告人简介：  嵇少林现为山东大学金融研究院教授、博士生导师，山东大学中泰证券金融研究院常务副院长，师从彭实戈院士。1999年至今在山东大学工作。研究领域为金融数学、金融经济学、随机优化和非线性期望理论。近年来，嵇少林与彭实戈教授、Larry Epstein教授、美周迅宇教授等合作者在《Review of financial studies》, 《Operations research》,《Probability theory and the related fields》和《SIAM Control and Optimization》等杂志上发表了一系列的成果。对金融市场中的学习理论、资本资产定价、随机优化问题和非线性期望理论进行了系统的研究。